CN116126655B

CN116126655B - Coal mining machine fault prompting method, system, storage medium and equipment

Info

Publication number: CN116126655B
Application number: CN202310344213.5A
Authority: CN
Inventors: 苏军军; 张阳; 钱江泳; 袁安祥; 苏龙龙
Original assignee: Changshu Tiandi Coal Mining Equipment Co ltd; Tiandi Shanghai Mining Equipment Technology Co Ltd
Current assignee: Changshu Tiandi Coal Mining Equipment Co ltd; Tiandi Shanghai Mining Equipment Technology Co Ltd
Priority date: 2023-04-03
Filing date: 2023-04-03
Publication date: 2023-06-23
Anticipated expiration: 2043-04-03
Also published as: CN116126655A

Abstract

The disclosure relates to a coal cutter fault prompting method, a system, a storage medium and equipment, which are applied to a fault detection device, wherein the fault detection device is in communication connection with a wearable wireless display device, and the method comprises the following steps: acquiring real-time state information of the coal mining machine, and updating the real-time state information into a state information queue; processing the real-time state information to obtain first display driving data; inputting the state information queue into a pre-trained fault detection model to obtain a fault detection result; obtaining second display driving data based on the fault detection result; and sending the first display driving data and the second display driving data to the wearable wireless display device so that the wearable wireless display device displays the current running state and the fault state of the coal mining machine. Whether the coal mining machine fails or not can be reliably determined, workers can be conveniently prompted through the wearable wireless display device, and the safety performance of the coal mining machine during working is effectively improved.

Description

Coal mining machine fault prompting method, system, storage medium and equipment

Technical Field

The disclosure relates to the field of coal mining, in particular to a coal cutter fault prompting method, a system, a storage medium and equipment.

Background

In the related technology, for state inquiry and fault prompt of the coal mining machine, as the proportion of the panel occupied by the buttons is higher and the display interface is smaller, only a few items of information can be selected for display, and the real-time fault adopts rolling prompt display and is not fully observed. When the working flour dust concentration is high, the display information of the coal mining machine is not easy to view. Meanwhile, the problem of low fault detection accuracy also exists.

Disclosure of Invention

This summary is provided to introduce a selection of concepts in a simplified form that are further described below in the detailed description. This summary is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used to limit the scope of the claimed subject matter.

According to a first aspect of embodiments of the present disclosure, there is provided a fault prompting method of a coal mining machine, applied to a fault detection device, where the fault detection device is communicatively connected to a wearable wireless display device, the method includes:

acquiring real-time state information of the coal mining machine, and updating the real-time state information into a state information queue;

processing the real-time state information to obtain first display driving data;

Inputting the state information queue into a pre-trained fault detection model to obtain a fault detection result;

obtaining second display driving data based on the fault detection result;

and sending the first display driving data and the second display driving data to the wearable wireless display device so that the wearable wireless display device displays the current running state and the fault state of the coal mining machine.

According to a second aspect of the embodiments of the present disclosure, there is provided a fault prompting system for a coal mining machine, including a fault detection device and a wearable wireless display device, the fault detection device being in communication connection with the wearable wireless display device, the fault detection device being configured to:

obtaining second display driving data based on the fault detection result;

According to a third aspect of embodiments of the present disclosure, there is provided a computer readable medium having stored thereon a computer program which, when executed by a processing device, performs the steps of the method of any of the first aspects of the present disclosure.

According to a fourth aspect of embodiments of the present disclosure, there is provided an electronic device, comprising:

a storage device having a computer program stored thereon;

processing means for executing the computer program in the storage means to carry out the steps of the method according to any one of the first aspects of the present disclosure.

By utilizing the technical scheme, the real-time state information of the coal mining machine is acquired through the fault detection unit, the fault information of the coal mining machine is determined based on the state information queue corresponding to the real-time state information, and meanwhile, the state information and the driving data corresponding to the fault information are sent to the wearable wireless display device, so that the wearable wireless display device can display the current state of the coal mining machine and the current fault condition, whether the coal mining machine fails or not can be reliably determined, workers can be conveniently prompted through the wearable wireless display device, the safety performance of the coal mining machine during working is effectively improved, and the personal safety of operators of the coal mining machine is reliably ensured.

Additional features and advantages of the present disclosure will be set forth in the detailed description which follows.

Drawings

The above and other features, advantages, and aspects of embodiments of the present disclosure will become more apparent by reference to the following detailed description when taken in conjunction with the accompanying drawings. The same or similar reference numbers will be used throughout the drawings to refer to the same or like elements. It should be understood that the figures are schematic and that elements and components are not necessarily drawn to scale. In the drawings:

FIG. 1 is a flow chart illustrating a method of coal cutter fault notification according to an exemplary embodiment.

FIG. 2 is a schematic diagram illustrating a shearer fault notification system according to an example embodiment.

Fig. 3 is a block diagram of an electronic device, according to an example embodiment.

Detailed Description

Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While certain embodiments of the present disclosure have been shown in the accompanying drawings, it is to be understood that the present disclosure may be embodied in various forms and should not be construed as limited to the embodiments set forth herein, but are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are for illustration purposes only and are not intended to limit the scope of the present disclosure.

It should be understood that the various steps recited in the method embodiments of the present disclosure may be performed in a different order and/or performed in parallel. Furthermore, method embodiments may include additional steps and/or omit performing the illustrated steps. The scope of the present disclosure is not limited in this respect.

The term "including" and variations thereof as used herein are intended to be open-ended, i.e., including, but not limited to. The term "in accordance with" is at least partially in accordance with ". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments. Related definitions of other terms will be given in the description below.

It should be noted that the terms "first," "second," and the like in this disclosure are merely used to distinguish between different devices, modules, or units and are not used to define an order or interdependence of functions performed by the devices, modules, or units.

It should be noted that references to "one", "a plurality" and "a plurality" in this disclosure are intended to be illustrative rather than limiting, and those of ordinary skill in the art will appreciate that "one or more" is intended to be understood as "one or more" unless the context clearly indicates otherwise.

The names of messages or information interacted between the various devices in the embodiments of the present disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

The operating electronic device, application, server, or storage medium, etc. software or hardware provides the personal information.

Meanwhile, it can be understood that the data (including but not limited to the data itself, the acquisition or the use of the data) related to the technical scheme should conform to the requirements of the corresponding laws and regulations and related regulations.

In the related technology, the state inquiry and fault prompt of the coal mining machine go through three development stages, namely an original visual direct observation stage, a sound early warning stage and a current symbol graphic display stage. At present, the coal cutter can inquire state information through an onboard display screen of the coal cutter, and can also check partial information through a micro display screen carried by a wireless remote controller of the coal cutter, but due to the limitation of working conditions, a driver of the coal cutter can conveniently operate the onboard display screen to check the information and fault records of the coal cutter under the stop state of the coal cutter. The existing remote controller has the defects that the proportion of the panel occupied by the buttons is high, the display interface is small, only a few items of information can be selected for display, the real-time faults are displayed by adopting rolling prompt, and the observation is not comprehensive. When the working flour dust concentration is high, the display information of the coal mining machine is not easy to view. Meanwhile, due to the variety of fault types of the coal mining machine, it is difficult to accurately determine what kind of faults exist in the coal mining machine, and the problem of low fault detection accuracy exists.

Based on this, the embodiments of the present disclosure provide a method, a system, a storage medium, and an apparatus for prompting a fault of a coal mining machine, so as to overcome the problems in the related art.

FIG. 1 is a flow chart illustrating a shearer fault prompting method according to an exemplary embodiment applied to a fault detection device communicatively coupled to a wearable wireless display device, which may be, for example, a head mounted display. The communication connection may be, for example, a bluetooth connection, or a WiFi connection, or through a cellular network connection, etc., as the present disclosure is not limited in this regard.

As shown in fig. 1, the method includes:

s101, acquiring real-time state information of the coal mining machine, and updating the real-time state information into a state information queue.

Alternatively, the real-time state information of the shearer may include, for example, information of a current input power, an output power, a voltage of a shearer drum, hydraulic system pressure information, current information, temperature information, a rocker arm inclination angle, a three-dimensional space position, a shearer cutting state, and the like of the shearer, which is not particularly limited in the embodiments of the disclosure.

It will be appreciated that the state information queue may include N pieces of real-time state information collected at different times, and when new real-time state information is updated to the state information queue, the oldest real-time state information at the end of the sequence may be deleted. In this way, it is possible to detect whether the shearer is malfunctioning while occupying a minimum of storage space.

S102, processing the real-time state information to obtain first display driving data.

For example, after the current various state data are screened or combined, first display driving data for driving the wearable wireless display device can be obtained, so that the wearable wireless display device can display an image corresponding to the real-time state information, and further, a worker can intuitively view the current state information of the coal mining machine.

S103, inputting the state information queue into a pre-trained fault detection model to obtain a fault detection result.

Specifically, whether or not the shearer is currently malfunctioning may be determined based on the status information queue, or what kind of malfunction is present may also be determined.

In some embodiments, the fault detection model may be sent to the fault detection apparatus after being trained on other electronic devices, or may be trained in the fault detection apparatus, which is not limited by the present disclosure.

And S104, obtaining second display driving data based on the fault detection result.

It can be appreciated that when the fault detection result indicates that a certain fault exists, the wearable wireless display device can be driven based on the second display driving data, so that the wearable wireless display device displays corresponding fault information, and further, a worker can troubleshoot the fault.

S105, the first display driving data and the second display driving data are sent to the wearable wireless display device, so that the wearable wireless display device displays the current running state and the fault state of the coal mining machine.

In the embodiment of the disclosure, the real-time state information of the coal mining machine is acquired through the fault detection unit, the fault information of the coal mining machine is determined based on the state information queue corresponding to the real-time state information, and meanwhile, the state information and the driving data corresponding to the fault information are sent to the wearable wireless display device, so that the wearable wireless display device can display the current state of the coal mining machine and the current fault condition, whether the coal mining machine fails or not can be reliably determined, workers can be conveniently prompted through the wearable wireless display device, the safety performance of the coal mining machine during working is effectively improved, and the personal safety of operators of the coal mining machine is reliably ensured.

In some optional embodiments, inputting the state information queue into a pre-trained fault detection model to obtain a fault detection result, including:

and inputting the state information queue into a fault detection model, determining a state characteristic vector corresponding to the state information queue, wherein the fault detection model is used for detecting one or more faults of the coal mining machine.

A target example vector is obtained that corresponds to each of a plurality of example state queues that correspond to one or more shearer faults.

And determining the confidence parameters corresponding to the state information queues based on the state feature vectors and the target example vectors respectively corresponding to the plurality of example state queues.

And determining a fault cluster of the state information queue based on the confidence parameter, wherein the fault cluster is a first fault cluster comprising one or more coal cutter faults identifiable by a fault detection model or a second fault cluster not comprising one or more coal cutter faults identifiable by the fault detection model.

And determining that the target coal mining machine corresponding to the state information queue under the first fault cluster is faulty in response to the state information queue corresponding to the first fault cluster.

In this embodiment, a fault detection model capable of identifying one or more shearer faults may be pre-trained based on a plurality of example status queues corresponding to the one or more shearer faults. The model training process of the fault detection model will be described in detail below. Since the model training process is similar to the process of using models to identify behavior of a state information queue, only the process of using models will be described first.

In the fault detection process, an important role played by the fault detection model is feature engineering, which comprises the following steps: the method comprises the steps of determining state characteristic vectors of a state information queue and determining state characteristic vectors corresponding to a plurality of example state queues respectively.

For convenience of distinction, in this embodiment, the state feature vectors corresponding to the plurality of example state queues are referred to as target example vectors, and the state feature vectors hereinafter refer to the state feature vectors of the state information queues.

When determining the state characteristic vector of the state information queue, the working process of the fault detection model is as follows:

sampling the input state information queue by using a data sampling unit to determine real-time state information comprising multiple moments;

sampling real-time state information at multiple moments in a state information queue by utilizing a feature engineering unit to determine a plurality of feature vectors corresponding to the state information queue;

and carrying out pooling treatment on the plurality of feature vectors to determine the state feature vector corresponding to the state information queue.

The process of obtaining the target example vector corresponding to each of the plurality of example state queues is similar to the process of determining the state feature vector of the state information queue, specifically, the plurality of example state queues may be sequentially input into the trained fault detection model, and the target example vector corresponding to each of the plurality of example state queues is determined.

After the state feature vector and the target example vectors respectively corresponding to the plurality of example state queues are obtained, a probability that the state information queue corresponds to the second failure cluster may be determined based on the state feature vector and the plurality of target example vectors. In this embodiment, the confidence parameter is used to represent the probability that the state information queue corresponds to the second failure cluster.

In the implementation process, optionally, the feature distribution parameters corresponding to the plurality of sample state queues may be determined based on the target sample vectors corresponding to the plurality of sample state queues; then, based on the feature distribution parameters corresponding to the state feature vector and the plurality of example state queues, confidence parameters corresponding to the state information queues are determined. Wherein the feature distribution parameters include: and parameter average and parameter relation matrix of the target example vector corresponding to the plurality of example state queues respectively.

Optionally, determining the confidence parameter corresponding to the state information queue based on the state feature vector and the target sample vector respectively corresponding to the plurality of sample state queues includes the following steps:

determining characteristic distribution parameters corresponding to the plurality of sample state queues based on target sample vectors corresponding to the plurality of sample state queues respectively, wherein the characteristic distribution parameters comprise parameter average and parameter relation matrixes of the plurality of target sample vectors; the parameter relation matrix may be, for example, a covariance matrix;

Determining a parametric bias value between the state feature vector and a parametric average of the plurality of target example vectors;

and determining the confidence parameters corresponding to the state information queue based on the parameter deviation values and the parameter relation matrix.

Optionally, determining the confidence parameter corresponding to the state information queue based on the parameter deviation value and the parameter relation matrix includes:

and determining the product of the transposition of the parameter deviation value, the inverse of the parameter relation matrix and the parameter deviation value as a confidence parameter corresponding to the state information queue.

The confidence parameter is used for representing the probability that the state information queue corresponds to the second fault cluster, in practical application, a confidence parameter threshold value can be preset, and the state information queue is determined to correspond to the first fault cluster or the second fault cluster based on the magnitude relation between the actually calculated confidence parameter and the confidence parameter threshold value. Such as: when the confidence parameter corresponding to the state information queue is larger than the confidence parameter threshold value, determining that the state information queue corresponds to a second fault cluster; and when the confidence parameter corresponding to the state information queue is smaller than or equal to the confidence parameter threshold value, determining that the state information queue corresponds to the first fault cluster.

Optionally, in response to the state information queue corresponding to the second fault cluster, outputting prompt information for prompting a new coal cutter fault marking on the state information queue, so as to perform optimization training on the fault detection model.

The method for determining the target coal mining machine faults corresponding to the state information queues under the first fault clusters comprises the following steps:

acquiring one or more example cluster characteristics corresponding to faults of the coal mining machine respectively, wherein the example cluster characteristics are iteratable variables in a fault detection model;

and determining the target coal cutter faults corresponding to the state information queue under the first fault cluster based on the distances between the state feature vectors and the example cluster vectors respectively corresponding to the one or more coal cutter faults. In an alternative embodiment, the cosine distance between the calculated state feature vector and the example cluster vector corresponding to one or more coal cutter faults, respectively, may be used to determine the corresponding distance.

Exemplary cluster characteristics of a shearer fault may be understood as generic characteristics of the shearer fault. When the fault detection model is trained, a cluster feature is generally initialized for each coal cutter fault at random for representing the general feature of each coal cutter fault, and then the cluster feature is continuously adjusted in the training process, so that after the fault detection model is trained, the example cluster feature which can truly and correctly represent the general feature of each coal cutter fault is obtained.

Because the information included in the example cluster features of different categories is different, the target shearer fault corresponding to the state information queue can be determined based on the distance between the state feature vector and the example cluster vector.

The distance between the example clustering feature corresponding to the target coal cutter fault and the state feature vector is larger than the distance between the example clustering feature corresponding to other coal cutter faults and the state feature vector.

In summary, in the scheme provided by the embodiment of the invention, the confidence parameters of the state information queues are determined based on the characteristics of the state information queues and the target example vectors respectively corresponding to the plurality of example state queues; then, determining whether the state information queue corresponds to the first fault cluster or the second fault cluster based on the confidence parameter, and further determining that the state information queue corresponds to the target coal mining machine fault under the first fault cluster when the state information queue corresponds to the first fault cluster. Therefore, the state information queue corresponding to the first fault cluster can be accurately recognized, whether the state information queue corresponds to the second fault cluster can be effectively detected, the state information queue corresponding to the second fault cluster can be prevented from being erroneously classified under a certain first fault cluster, and therefore the accuracy of a fault detection result can be improved.

The use process of the fault detection model is described above, and the training process of the fault detection model is described below.

In some alternative embodiments the fault detection model training method may include the steps of:

a first example state queue and a plurality of second example state queues corresponding to the first coal cutter fault are obtained.

A first example vector corresponding to the first example state queue and a plurality of second example vectors corresponding to the plurality of second example state queues are determined using the fault detection model.

Determining a first distance between the first example vector and a cluster vector corresponding to the first coal cutter fault, which is determined by the fault detection model, and a second distance between the first example vector and a vector in a first vector combination, wherein the first vector combination comprises a plurality of second example vectors.

Determining a second vector combination, wherein the second vector combination comprises a cluster characteristic corresponding to the fault of the second coal mining machine and an example vector corresponding to an example state queue corresponding to the fault of the second coal mining machine, which are obtained by determining a fault detection model; wherein the second shearer fault comprises one or more shearer faults other than the first shearer fault.

A third distance between the vectors in the first example vector and the second vector combination is determined.

Determining training cost values corresponding to the first example state queue based on the first distance, the second distance and the third distance by taking the first distance and the second distance as training conditions; and training a fault detection model based on the training cost value.

The fault detection model is trained based on the training cost value, namely, model parameters are iterated by using back propagation. The model parameters comprise clustering features corresponding to faults of each coal mining machine, and the fault detection model can utilize continuous learning to adjust the clustering features of the faults of each coal mining machine during training.

Specifically, to perform training of the fault detection model, a large number of example state queues (i.e., the plurality of example state queues above) corresponding to one or more shearer faults need to be obtained in advance. In training the fault detection model, for each shearer fault, a corresponding example set, i.e., training set, may be provided, including a plurality of example state queues.

Alternatively, the shearer faults may include, for example, shearer hydraulic system faults, loss of temperature faults, shearer cutter faults, rocker arm faults, circuit faults, and the like, to which embodiments of the present disclosure are not limited.

For example, assume that a fault detection model is to be trained to perform fault detection on X kinds of coal cutter faults, and for a certain one of the X kinds of coal cutter faults, such as a hydraulic system fault, the fault detection model is referred to as a first coal cutter fault in this embodiment, and other X-1 kinds of coal cutter faults except the first coal cutter fault are referred to as second coal cutter faults. Assume that the set of examples corresponding to the first shearer fault includes Y example state queues, and for one example state queue of the Y example state queues, in this embodiment, the first example state queue is referred to as a first example state queue, and all other example state queues except the first training sample are referred to as second example state queues.

First, a first example state queue and a plurality of second example state queues corresponding to a first coal cutter fault are obtained.

Optionally, a first example set corresponding to the first coal cutter fault may be obtained first; then, carrying out data augmentation processing on an example state queue included in the first example set to determine a second example set; thereafter, a first example state queue and a plurality of second example state queues are obtained from the second example set. In this way, the number of samples can be enlarged using the augmentation process.

Then, a fault detection model is utilized to determine a first example vector corresponding to the first example state queue and a plurality of second example vectors corresponding to the plurality of second example state queues. The determination process may refer to the relevant description in the foregoing embodiments, which is not repeated here.

In practice, during the training process, the fault detection model may also be used to determine the example vector of the example state queue corresponding to the fault of the second shearer.

In this embodiment, for convenience of description, two vector sets, a first vector combination and a second vector combination, respectively, are defined. Wherein the first vector combination includes a plurality of determined second example vectors, i.e., example vectors corresponding to a plurality of second example state queues corresponding to the first shearer fault; the second vector combination comprises cluster features corresponding to the faults of the second coal mining machine, which are determined by the fault detection model, and example vectors of an example state queue corresponding to the faults of the second coal mining machine. It should be noted that, the cluster features corresponding to the second coal cutter faults obtained by the fault detection model are actually the X-1 cluster features corresponding to the other X-1 coal cutter faults except the first coal cutter faults, and can be understood as a feature set.

And then, performing distance calculation on the first example vector and the cluster characteristic corresponding to the first coal cutter fault determined by the fault detection model to determine a first distance between the first example vector and the cluster vector corresponding to the first coal cutter fault determined by the fault detection model. Since the cluster features corresponding to the different shearer faults are used to distinguish between the different shearer faults, the calculation of the first distance is actually used to measure the probability that the first example state queue corresponds to the first shearer fault.

And performing distance calculation on the first example vector and each vector in the first vector combination, and determining a second distance between the first example vector and each vector in the first vector combination. Since the first vector combination corresponds to a plurality of second example state queues in the first shearer fault, the calculation of the second distance is effective to distinguish between differences between different example state queues in the first shearer fault.

And performing distance calculation on each vector in the first example vector and the second vector combination, and determining a third distance between each vector in the first example vector and the second vector combination. The calculation of the third distance is effective to measure the difference between the first example state queue and each second shearer fault in the first shearer fault, since the second vector combination includes the cluster feature of each second shearer fault and the example vector of each example state queue of each second shearer fault.

Alternatively, the distance in this embodiment may be determined by calculating the Euclidean distance between vectors.

And then, taking the first distance and the second distance as training conditions, determining a training cost value corresponding to the first example state queue based on the first distance, the second distance and the third distance, and iterating the fault detection model based on the training cost value. Wherein the distance threshold is set to a value less than 1.

It can be appreciated that, taking the set distance threshold value close to less than 1 as a training condition, the difference between the first example vector and the clustering vector of the first coal cutter fault and the difference between each feature (i.e. a plurality of second example vectors) in the first example vector and the first vector combination can be kept, i.e. the model can learn more abundant information.

In summary, in this embodiment, based on the setting of the distance threshold value smaller than 1, for a plurality of example state queues corresponding to a certain coal cutter fault, the model can learn the difference characteristics of different example state queues of the same coal cutter fault, thereby being beneficial to improving the accuracy of fault detection.

In some alternative embodiments, the method may further comprise the steps of:

Performing sequence random arrangement operation on the first example state queue to obtain a third example state queue; and determining a third example vector corresponding to the third example state queue by using the fault detection model.

Determining a first distance between the first example vector and a cluster vector corresponding to the first coal cutter fault determined by the fault detection model, and a second distance between the first example vector and a vector in a first vector combination respectively, wherein the first vector combination comprises a plurality of second example vectors and a plurality of third example vectors.

In this embodiment, a third example state queue is introduced during model training. The third example state queue is obtained after the first example state queue is subjected to sequence random arrangement operation, and the sequence random arrangement operation is utilized to amplify the example state queue in the time dimension, so that the capability of the fault detection model for determining time dimension information is enhanced, and the classification capability of the fault detection model for the first fault cluster and the classification capability of the fault cluster are enhanced.

In some embodiments, the first example state queue and the plurality of second example state queues corresponding to the first coal cutter fault may be first obtained, and the sequence random arrangement operation may be performed on the first example state queue to obtain a third example state queue. Then, a fault detection model is utilized to determine a first example vector corresponding to the first example state queue, a plurality of second example vectors corresponding to the plurality of second example state queues, and a third example vector corresponding to the third example state queue. Updating the third example vector to a first vector combination, wherein the first vector combination comprises a plurality of second example vectors and the third example vector, and the second vector combination comprises the cluster characteristics corresponding to the second coal cutter faults and the example vectors of the example state queues corresponding to the second coal cutter faults, which are determined by the fault detection model.

And then, calculating a first distance between the first example vector and the cluster vector corresponding to the first coal cutter fault, which is determined by the fault detection model, and a second distance between the first example vector and the vector in the first vector combination, and a third distance between the first example vector and the vector in the second vector combination.

Finally, the first distance and the second distance are reduced to be training conditions, and training cost values corresponding to the first example state queue are determined based on the first distance, the second distance and the third distance; and training a fault detection model based on the training cost value.

In summary, a third example vector corresponding to the third example state queue obtained after the sequence random arrangement operation is performed on the first example state queue is added to the first vector combination. The distance between the first sample vector and the third sample vector is reduced as a training condition, so that on one hand, similarity of the state information of the third sample state queue and the state information of the first sample state queue obtained after the sequence random arrangement operation can be ensured, and on the other hand, the difference of the time information of the third sample state queue and the time information of the first sample state queue can be ensured. Therefore, the fault detection model training method in the embodiment is not only beneficial to determining the fault cluster of the state information queue, but also can enhance the classification effect of the first fault cluster, and greatly improves the fault detection performance.

In some embodiments, the method may further comprise:

inputting a state information queue into a fault detection model, and determining a state feature vector corresponding to the state information queue, wherein the fault detection model is used for detecting one or more faults of the coal mining machine;

obtaining target example vectors respectively corresponding to a plurality of example state queues, wherein the plurality of example state queues correspond to the one or more faults of the coal mining machine;

determining a confidence parameter corresponding to the state information queue based on the state feature vector and target example vectors respectively corresponding to the plurality of example state queues;

determining a fault cluster of the state information queue based on the confidence parameter, wherein the fault cluster is a first fault cluster comprising the one or more coal cutter faults or a second fault cluster not comprising the one or more coal cutter faults;

and determining that the state information queue corresponds to the target coal cutter fault under the first fault cluster in response to the state information queue corresponding to the first fault cluster.

The above execution may refer to the related descriptions in the other embodiments, which are not described in detail herein.

Fig. 2 is a schematic diagram of a fault notification system of a coal mining machine, and as shown in fig. 2, the fault notification system 200 of the coal mining machine includes a fault detection device 210 and a wearable wireless display device 220, where the fault detection device 210 is communicatively connected to the wearable wireless display device 220, and the fault detection device 210 is configured to:

inputting the real-time state driving data of the state information queue into a pre-trained fault detection model to obtain a fault detection result;

obtaining second display driving data according to the fault detection result;

the first display driving data and the second display driving data are sent to the wearable wireless display device 220, so that the wearable wireless display device 220 displays the current running state and the fault state of the coal mining machine.

Optionally, the inputting the state information queue into a pre-trained fault detection model to obtain a fault detection result includes:

inputting the state information queue into the fault detection model, and determining a state feature vector corresponding to the state information queue, wherein the fault detection model is used for detecting one or more faults of the coal mining machine;

Optionally, the determining the target coal cutter fault corresponding to the state information queue under the first fault cluster includes:

acquiring example clustering features corresponding to one or more faults of the coal mining machine respectively, wherein the example clustering features are iteratable variables in the fault detection model;

and determining a target coal cutter fault corresponding to the state information queue under the first fault cluster based on the distance between the state characteristic vector and the example cluster vector corresponding to the one or more coal cutter faults respectively.

Optionally, the determining, based on the state feature vector and the target example vectors respectively corresponding to the plurality of example state queues, a confidence parameter corresponding to the state information queue includes:

determining characteristic distribution parameters corresponding to the plurality of sample state queues based on target sample vectors corresponding to the plurality of sample state queues respectively;

determining a confidence parameter corresponding to the state information queue based on the state feature vector and feature distribution parameters corresponding to the plurality of example state queues;

the characteristic distribution parameters include: and parameter average and parameter relation matrixes of the target example vectors respectively corresponding to the plurality of example state queues.

Optionally, the obtaining target sample vectors corresponding to the plurality of sample state queues respectively includes:

and sequentially inputting the plurality of sample state queues into the trained fault detection model, and determining target sample vectors respectively corresponding to the plurality of sample state queues.

Optionally, the training of the fault detection model includes:

acquiring a first example state queue and a plurality of second example state queues corresponding to the faults of the first coal mining machine;

determining a first example vector corresponding to the first example state queue and a plurality of second example vectors corresponding to the plurality of second example state queues using the fault detection model;

Determining a first distance between the first example vector and a cluster vector corresponding to the first coal mining machine fault, which is determined by the fault detection model, and a second distance between the first example vector and a vector in a first vector combination, wherein the first vector combination comprises a plurality of second example vectors;

determining a second vector combination, wherein the second vector combination comprises a cluster characteristic corresponding to the second coal cutter fault and an example vector corresponding to an example state queue corresponding to the second coal cutter fault, which are determined by the fault detection model; wherein the second shearer fault comprises a shearer fault other than the first shearer fault of the one or more shearer faults;

determining a third distance between vectors in the first example vector and the second vector combination;

determining a training cost value corresponding to the first example state queue based on the first distance, the second distance and the third distance by taking the first distance and the second distance as training conditions;

and iterating the fault detection model based on the training cost value.

Optionally, the fault detection device 210 is further configured to:

Performing sequence random arrangement operation on the first example state queue to obtain a third example state queue;

determining a third example vector corresponding to the third example state queue using the fault detection model;

updating the third example vector into the first vector combination.

Referring now to fig. 3, a schematic diagram of an electronic device 300 suitable for use in implementing embodiments of the present disclosure is shown. The electronic device 300 in the embodiments of the present disclosure may include, but is not limited to, mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and the like, and stationary terminals such as digital TVs, desktop computers, and the like. For example, the electronic device 300 may also be provided as a fault detection device or a wearable wireless display device. The electronic device shown in fig. 3 is merely an example and should not be construed to limit the functionality and scope of use of the disclosed embodiments.

As shown in fig. 3, the electronic device 300 may include a processing means (e.g., a central processing unit, a graphics processor, etc.) 301 that may perform various suitable actions and processes in accordance with a program stored in a Read Only Memory (ROM) 302 or a program loaded from a storage means 308 into a Random Access Memory (RAM) 303. In the RAM 303, various programs and data required for the operation of the electronic apparatus 300 are also stored. The processing device 301, the ROM 302, and the RAM 303 are connected to each other via a bus 304. An input/output (I/O) interface 305 is also connected to bus 304.

In general, the following devices may be connected to the I/O interface 305: input devices 306 including, for example, a touch screen, touchpad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; an output device 307 including, for example, a Liquid Crystal Display (LCD), a speaker, a vibrator, and the like; storage 308 including, for example, magnetic tape, hard disk, etc.; and communication means 309. The communication means 309 may allow the electronic device 300 to communicate with other devices wirelessly or by wire to exchange data. While fig. 3 shows an electronic device 300 having various means, it is to be understood that not all of the illustrated means are required to be implemented or provided. More or fewer devices may be implemented or provided instead.

In particular, according to embodiments of the present disclosure, the processes described above with reference to flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a non-transitory computer readable medium, the computer program comprising program code for performing the method shown in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network via a communication device 309, or installed from a storage device 308, or installed from a ROM 302. The above-described functions defined in the methods of the embodiments of the present disclosure are performed when the computer program is executed by the processing means 301.

It should be noted that the computer readable medium described in the present disclosure may be a computer readable signal medium or a computer readable storage medium, or any combination of the two. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this disclosure, a computer-readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In the present disclosure, however, the computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, with the computer-readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, fiber optic cables, RF (radio frequency), and the like, or any suitable combination of the foregoing.

In some embodiments, the fault detection device and the wearable wireless display device may communicate using any currently known or future developed network protocol, such as HTTP (HyperTextTransfer Protocol ), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), the internet (e.g., the internet), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future developed networks.

The computer readable medium may be contained in the electronic device; or may exist alone without being incorporated into the electronic device.

The computer readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to perform some or all of the steps involved in the method embodiments described above.

Alternatively, the computer readable medium carries one or more programs, which when executed by the electronic device, cause the electronic device to perform some or all of the steps involved in the method embodiments described above.

Computer program code for carrying out operations of the present disclosure may be written in one or more programming languages, including, but not limited to, an object oriented programming language such as Java, smalltalk, C ++ and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computer (for example, through the Internet using an Internet service provider).

The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The modules described in the embodiments of the present disclosure may be implemented in software or hardware. The name of a module does not in some cases define the module itself.

The functions described above herein may be performed, at least in part, by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: a Field Programmable Gate Array (FPGA), an Application Specific Integrated Circuit (ASIC), an Application Specific Standard Product (ASSP), a system on a chip (SOC), a Complex Programmable Logic Device (CPLD), and the like.

In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. The machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

The foregoing description is only of the preferred embodiments of the present disclosure and description of the principles of the technology being employed. It will be appreciated by persons skilled in the art that the scope of the disclosure referred to in this disclosure is not limited to the specific combinations of features described above, but also covers other embodiments which may be formed by any combination of features described above or equivalents thereof without departing from the spirit of the disclosure. Such as those described above, are mutually substituted with the technical features having similar functions disclosed in the present disclosure (but not limited thereto).

Moreover, although operations are depicted in a particular order, this should not be understood as requiring that such operations be performed in the particular order shown or in sequential order. In certain circumstances, multitasking and parallel processing may be advantageous. Likewise, while several specific implementation details are included in the above discussion, these should not be construed as limiting the scope of the present disclosure. Certain features that are described in the context of separate embodiments can also be implemented in combination in a single embodiment. Conversely, various features that are described in the context of a single embodiment can also be implemented in multiple embodiments separately or in any suitable subcombination.

Although the subject matter has been described in language specific to structural features and/or methodological acts, it is to be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are example forms of implementing the claims. The specific manner in which the various modules perform the operations in the apparatus of the above embodiments have been described in detail in connection with the embodiments of the method, and will not be described in detail herein.

Claims

1. A fault prompting method for a coal mining machine, which is characterized by being applied to a fault detection device, wherein the fault detection device is in communication connection with a wearable wireless display device, and the method comprises the following steps:

obtaining second display driving data based on the fault detection result;

transmitting the first display driving data and the second display driving data to the wearable wireless display device so that the wearable wireless display device displays the current running state and the fault state of the coal mining machine,

The step of inputting the state information queue into a pre-trained fault detection model to obtain a fault detection result comprises the following steps:

in response to the status information queue corresponding to the first failure cluster, determining a target shearer failure for which the status information queue corresponds under the first failure cluster,

the determining the target coal cutter fault corresponding to the state information queue under the first fault cluster includes:

determining a target shearer fault corresponding to the state information queue under the first fault cluster based on distances between the state feature vector and the example cluster vectors respectively corresponding to the one or more shearer faults,

wherein the determining, based on the state feature vector and the target example vectors respectively corresponding to the plurality of example state queues, the confidence parameter corresponding to the state information queue includes:

the characteristic distribution parameters include: the plurality of sample state queues respectively correspond to the parameter average and parameter relation matrix of the target sample vector,

the obtaining the target example vectors corresponding to the plurality of example state queues respectively includes:

Sequentially inputting the plurality of sample state queues into the trained fault detection model, determining target sample vectors respectively corresponding to the plurality of sample state queues,

the parameter relation matrix is a covariance matrix, parameter deviation values between the state characteristic vector and parameter averages of the target sample vectors are determined, and products of the transpose of the parameter deviation values, the inverse of the parameter relation matrix and the parameter deviation values are determined to be confidence parameters corresponding to a state information queue.

2. The method of claim 1, wherein the training of the fault detection model comprises:

and iterating the fault detection model based on the training cost value.

3. The method according to claim 2, wherein the method further comprises:

updating the third example vector into the first vector combination.

4. A shearer fault prompting system, characterized by comprising a fault detection device and a wearable wireless display device, wherein the fault detection device is in communication connection with the wearable wireless display device, and the fault detection device is used for executing the shearer fault prompting method according to any one of the preceding claims 1-3.

5. A computer readable medium on which a computer program is stored, characterized in that the program, when being executed by a processing device, carries out the steps of the method according to any one of claims 1-3.

6. An electronic device, comprising:

a storage device having a computer program stored thereon;

processing means for executing said computer program in said storage means to carry out the steps of the method of any one of claims 1-3.